CN111401057B - Semantic analysis method, storage medium and terminal equipment - Google Patents
Semantic analysis method, storage medium and terminal equipment Download PDFInfo
- Publication number
- CN111401057B CN111401057B CN201811643289.3A CN201811643289A CN111401057B CN 111401057 B CN111401057 B CN 111401057B CN 201811643289 A CN201811643289 A CN 201811643289A CN 111401057 B CN111401057 B CN 111401057B
- Authority
- CN
- China
- Prior art keywords
- voice information
- application set
- information
- set corresponding
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 22
- 238000000034 method Methods 0.000 claims abstract description 32
- 238000004891 communication Methods 0.000 claims description 10
- 238000003058 natural language processing Methods 0.000 description 6
- 239000011159 matrix material Substances 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Landscapes
- Machine Translation (AREA)
Abstract
The invention discloses a semantic analysis method, a storage medium and terminal equipment, wherein the method comprises the following steps: when voice information is received, acquiring an application set corresponding to the voice information; when the application set corresponding to the voice information is not obtained, searching the voice information in a preset voice information database; if the voice information is not found, determining an application set corresponding to the voice information by adopting an LFM model; and analyzing the voice information in the application set to obtain an analysis text of the voice information. According to the invention, the LFM model is adopted to determine the application set corresponding to the voice information, and the voice information is analyzed according to the application set corresponding to the voice information, so that the success rate of voice information analysis is improved.
Description
Technical Field
The invention relates to the technical field of voice interaction, in particular to a semantic analysis method, a storage medium and terminal equipment.
Background
Natural language processing (Natural Language Processing, NLP) is a branch discipline in the fields of artificial intelligence and linguistics. The issues covered by natural language processing are quite broad and include: broken words (word segmentation), part-of-speech tagging (name entity tagging), proper noun tagging (name entity tagging), word sense disambiguation (wordsense disambiguation), alternative noun paraphrasing (pronoun resolution), syntactic parsing, grammar comparison, semantic role tagging (semantic role labeling), semantic logic inference, automatic transliteration, machine translation, speech recognition, speech synthesis, and the like.
At present, when natural language processing is adopted to analyze voice information, text information corresponding to the voice information is classified according to preset classification rules, and the voice information is analyzed according to combination of the classifications. Wherein the classification may include application set information, intention information, and attribute information. For example, in the phrase "what is the case for Shenzhen tomorrow weather", NLP can get the following semantic results: application aggregation information (Domain): weather; intent information (Intent): inquiring weather; attribute information (property): city (city) =Shenzhen, time (date) =open day. However, when the user statement is missing and the application set to which the voice information belongs cannot be determined, the resolution success rate is reduced.
Disclosure of Invention
In view of the defects in the prior art, the invention aims to provide a semantic analysis method, a storage medium and terminal equipment so as to improve the success rate of semantic analysis.
The technical scheme adopted by the invention is as follows:
a semantic parsing method, comprising:
when voice information is received, acquiring an application set corresponding to the voice information;
when the application set corresponding to the voice information is not obtained, searching the voice information in a preset voice information database;
if the voice information is not found, determining an application set corresponding to the voice information by adopting an LFM model;
and analyzing the voice information in the application set to obtain an analysis text of the voice information.
The semantic analysis method, wherein when voice information is received, the obtaining the application set corresponding to the voice information specifically includes:
when voice information is received, analyzing the voice information to obtain text information corresponding to the voice information;
dividing the text information into a plurality of keywords, and determining an application set corresponding to the voice information according to each keyword obtained by dividing.
The semantic analysis method, wherein if the voice information is not found, determining the application set corresponding to the voice information by using an LFM model specifically includes:
if the voice information is not found, acquiring an application set corresponding to the voice information;
and calculating the correlation between the voice information and each application set by adopting an LFM model, and determining the application set corresponding to the voice information according to the correlation.
The semantic analysis method, wherein if the voice information is not found, the obtaining the application set corresponding to the voice information specifically includes:
if the voice information is not found, extracting each keyword carried by the voice information;
and determining an application set corresponding to the voice information according to all the extracted keywords.
The semantic analysis method, wherein the calculating the relevance between the voice information and each application set by using the LFM model, and determining the application set corresponding to the voice information according to the relevance specifically includes:
extracting text information corresponding to the voice information, and acquiring weight information of the text information in each application set;
acquiring the interestingness of the user corresponding to the voice information for each application set, and determining the relevance between the voice information and each application set according to the interestingness and the weight information;
and determining an application set corresponding to the voice information according to the correlation.
The semantic analysis method, wherein if the voice information is not found, determining the application set corresponding to the voice information by adopting an LFM model further comprises:
and associating the voice information with each application set, and storing the associated voice information in a preset voice information database.
The semantic parsing method, wherein the method further comprises the following steps:
when the voice information is searched, extracting application set information corresponding to the voice information, wherein the application set information comprises application sets corresponding to the voice information and the duty ratio of each application set;
and determining the application set corresponding to the voice information according to the duty ratio of each application set.
The application set corresponding to the voice information is determined according to the duty ratio of each application set, specifically:
and acquiring the duty ratio of each application set, and determining the application set corresponding to the voice information by adopting a preset linear predictor model.
A computer readable storage medium storing one or more programs executable by one or more processors to implement the steps in the semantic parsing method as described in any one of the above.
A terminal device, comprising: a processor, a memory, and a communication bus; the memory has stored thereon a computer readable program executable by the processor;
the communication bus realizes connection communication between the processor and the memory;
the processor, when executing the computer readable program, implements the steps in the semantic parsing method as described in any of the above.
The beneficial effects are that: compared with the prior art, the invention provides a semantic parsing method, a storage medium and terminal equipment, wherein the method comprises the following steps: when voice information is received, acquiring an application set corresponding to the voice information; when the application set corresponding to the voice information is not obtained, searching the voice information in a preset voice information database; if the voice information is not found, determining an application set corresponding to the voice information by adopting an LFM model; and analyzing the voice information in the application set to obtain an analysis text of the voice information. According to the invention, the LFM model is adopted to determine the voice information application set, and the voice information is analyzed according to the application set corresponding to the voice information, so that the success rate of voice information analysis is improved.
Drawings
Fig. 1 is a flowchart of a first embodiment of a semantic parsing method provided by the present invention.
Fig. 2 is a flowchart of step S30 in the first embodiment of the semantic parsing method provided by the present invention.
Fig. 3 is a flowchart of a second embodiment of a semantic parsing method provided by the present invention.
Fig. 4 is a schematic diagram of a linear predictor model in the second embodiment of the semantic parsing method provided by the present invention.
Fig. 5 is a schematic structural diagram of an embodiment of a terminal device provided by the present invention.
Detailed Description
The invention provides a semantic analysis method, a storage medium and a terminal device, and in order to make the purposes, technical schemes and effects of the invention clearer and more definite, the invention is further described in detail below by referring to the accompanying drawings and the embodiments. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless expressly stated otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. The term "and/or" as used herein includes all or any element and all combination of one or more of the associated listed items.
It will be appreciated by those skilled in the art that unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The invention will be further described by the description of embodiments with reference to the accompanying drawings.
Example 1
The embodiment provides a voice analysis method, as shown in fig. 1, including:
s10, when voice information is received, acquiring an application set corresponding to the voice information;
s20, searching the voice information in a preset voice information database when the application set corresponding to the voice information is not acquired;
s30, if the voice information is not found, determining an application set corresponding to the voice information by adopting an LFM model;
s40, analyzing the voice information in the application set to obtain an analysis text of the voice information.
Specifically, in the step S10, the voice information is received by the terminal device, which may be collected by the terminal device through a sound pickup configured by the terminal device, or may be sent to the terminal device by an external device connected to the terminal device. The terminal equipment is terminal equipment with a voice interaction function, such as a mobile phone, a tablet personal computer and the like. The application set is used for judging that the voice command corresponds to an application to be executed, and the application set can be multiple, for example, the application set can be a weather application set, a temperature application set, a humidity application set and the like.
In addition, the voice information can be processed by natural voice to obtain application set information, and the application set information can also be carried, so that when the voice information is received, whether the voice information carries keywords for expressing the application set or not needs to be judged. Correspondingly, when receiving the voice information, the acquiring the application set corresponding to the voice information specifically includes:
when voice information is received, analyzing the voice information to obtain text information corresponding to the voice information;
dividing the text information into a plurality of keywords, and determining an application set corresponding to the voice information according to each keyword obtained by dividing.
Specifically, the text information is obtained by text recognition of voice information, and after the text information is obtained, the text information is divided according to a sentence sequence so as to divide the text information into a plurality of keywords. For example, the text information corresponding to the voice information is "what the weather is in the open sky", and then the text information is divided into "what the weather is in the open sky", so that the weather is in the open sky ". After a plurality of keywords are obtained through division, whether keywords used for expressing an application set exist in all keywords or not is determined according to the keywords of each keyword. For example, in the above text information, weather expresses an application set, which is query weather. Of course, the text information corresponding to the voice information may not carry the keyword for expressing the application set, for example, "what is the case in the plain of Shenzhen". In this embodiment, when the text information corresponding to the voice information carries a keyword for expressing an application set, the application set corresponding to the keyword is used as the application set corresponding to the voice information, and when the text information corresponding to the voice information does not carry the keyword for expressing the application set, the voice information is searched in a preset voice information database.
Further, in the step S20, the voice information database is a database that is pre-established and is used for storing voice information, where the number of the corresponding application sets in any voice information in the voice information database is greater than or equal to 2. That is, each piece of voice information in the preset voice information database does not carry a keyword for expressing an application set, and the number of application sets to which each piece of voice information belongs is greater than two.
Further, in the step S30, the LFM (latent factor model) is a latent semantic model, which is a model commonly applied in a recommendation system, a relationship matrix between each application set corresponding to voice information and the voice information can be established through the LFM model, a duty ratio of the voice information in each application set can be determined according to the relationship matrix, and a service neighborhood corresponding to the voice information can be determined according to the duty ratio.
For example, as shown in fig. 2, if the voice information is not found, determining, by using the LFM model, an application set corresponding to the voice information specifically includes:
s31, if the voice information is not found, acquiring an application set corresponding to the voice information;
s32, calculating the correlation between the voice information and each application set by adopting an LFM model, and determining the application set corresponding to the voice information according to the correlation.
Specifically, the application set is an application set corresponding to the voice information, and the application set can be determined according to all keywords contained in the voice information. That is, when determining the application set corresponding to the voice information, the voice information may be converted into text information, the text information may be divided into a plurality of keywords, and the application set corresponding to the voice information may be determined according to all the keywords obtained by the division. Correspondingly, if the voice information is not found, acquiring the application set corresponding to the voice information specifically includes:
if the voice information is not found, extracting each keyword carried by the voice information;
and determining an application set corresponding to the voice information according to all the extracted keywords.
Specifically, the keyword information is obtained by dividing text information corresponding to the voice information according to sentence construction relations. Meanwhile, after the text information is divided according to sentence constitution relations, the keywords obtained through division can be screened according to the parts of speech and the meaning of the keywords, and an application set corresponding to the voice information is determined according to the screened keywords. In this embodiment, the filtering rule only retains the name and verb. Of course, the filtering rules may also retain keywords with actual meaning, and delete virtual words, adjectives, and adverbs. Therefore, the screening rule is adopted to screen the keywords obtained by division, the speed of reducing the acquisition of the application set can be improved, and meanwhile, the accuracy of the application set is improved.
Further, when the correlation between the voice information and each application set is calculated by adopting an LFM model, the correlation between the voice information and each application set can be determined according to the interest degree and the weight information by determining the interest degree of the user corresponding to the voice information and each application set and the weight information in each application set of the language information. Correspondingly, the calculating the correlation between the voice information and each application set by using the LFM model, and determining the application set corresponding to the voice information according to the correlation may include:
extracting text information corresponding to the voice information, and acquiring weight information of the text information in each application set;
acquiring the interestingness of the user corresponding to the voice information for each application set, and determining the relevance between the voice information and each application set according to the interestingness and the weight information;
and determining an application set corresponding to the voice information according to the correlation.
Specifically, the interest degree of the user corresponding to the voice information on each application set may be determined according to a history search record of the user and attribute features of the user, where the attribute features may include age, gender, hobbies and the like. The weight information is the weight of the voice information in each application set, and when a user inputs the voice information for the first time, the weight information of the voice information for each application set can be queried in a pre-stored corpus, wherein the corpus is pre-configured. Of course, in practical application, when obtaining the weight information of the voice information in each application set, the voice information may be divided into a plurality of corpora, and the weight information of the voice information in each application set is determined according to the plurality of corpora. When the voice information carries a plurality of linguistic data, for each application set, a first weight of each linguistic data can be obtained respectively, and then the weight information of the voice information in the application set is determined according to the first weight of each linguistic data. The weight information may be an average value of the first weights of the corpora, or a weighted result of the first weights of the corpora.
Further, in the step 40, after the voice information is parsed in the application set to obtain the parsed text of the voice information, the voice information is associated with each application set, and the associated voice information is stored in a preset voice information database, so that the voice information can be found in the preset voice information database when the voice information is received next time.
Example two
The embodiment provides a voice analysis method, as shown in fig. 3, including:
h10, when voice information is received, acquiring an application set corresponding to the voice information;
h20, searching the voice information in a preset voice information database when the application set corresponding to the voice information is not acquired;
h30, when the voice information is searched, extracting application set information corresponding to the voice information, wherein the application set information comprises application sets corresponding to the voice information and the duty ratio of each application set;
h40, determining an application set corresponding to the voice information according to the duty ratio of each application set;
and H50, analyzing the voice information in the first application set to obtain an analysis text of the voice information.
Specifically, in the present embodiment, the steps H10, H20 and H50 are the same as the steps S10, S20 and S40 in the first embodiment, and will not be described herein. Only steps H30 and H40 will be described here. In the step H30, the application set information is stored in the preset voice information database and is associated with the voice information. That is, when the voice information is found, the application set information stored in the preset voice information data may be extracted. When the duty ratio of each application set is obtained, predicting the application set corresponding to the voice information according to each obtained duty ratio, wherein the duty ratio is the probability that the application set is selected.
The determining, according to the duty ratio of each application set, the application set corresponding to the voice information specifically includes:
and acquiring the duty ratio of each application set, and determining the application set corresponding to the voice information by adopting a preset linear predictor model.
Specifically, the linear predictor model may be a model as shown in fig. 4, in which u (n-1), u (n-2), u (n-3), …, u (n-m) are the ratios of the voice information at each time instant to each application set, and the ratio of the application set corresponding to the voice information at each time instant is predicted from each ratio to beThe formula is:
wherein,is the tap coefficient.
Further, it can be known from the above formula that, after the tap coefficient is obtained, the duty ratio of the application set corresponding to the voice information at the predicted time n can be obtained. The tap coefficient calculating method comprises the following steps:
let e (n) be the error between the calculated domain duty cycle at time n and the predicted domain duty cycle at time n, then the error is defined as:
defining a cost function as a mean square error:
J＝E[e(n)e * (n)]＝E[|e(n)| 2 ]
the optimal filter needs to satisfy the orthogonality principle, let e 0 A specific value representing the estimated error of the filter operating under optimal conditions, the conditions being equivalent to:
and (5) expanding and finishing to obtain a wiener-Hough equation:
writing it in a matrix form:
R＝E[u(n)u H (n)]
wherein U (n) = [ U (n), U (n-1),. The term "U (n-m+1)] T R is an mxm correlation matrix consisting of tap inputs. Let P be the M x 1 cross-correlation vector of tap inputs and u (n):
P＝E[u(n)u * (n)]
the wiener hough equation can be reduced to:
RW 0 ＝P
wherein W is 0 Representing M1 tap weight vectors of optimal transversal filters, i.e.
W 0 ＝[W f,0 ,W f,1 ,......,W f,m-1 ] T 。
Furthermore, in another embodiment of the present invention, the method may further include:
determining the probability of each application set being selected according to the selected times of each application set;
extracting the maximum probability of the selected probability of each application set, and judging the number of the application sets corresponding to the maximum probability;
and when the number of the application sets is greater than 1, selecting the application set corresponding to the voice information from the application sets corresponding to the maximum probability according to a time preference principle.
Specifically, the application set corresponding to the maximum probability may be multiple, and at this time, the application set corresponding to the voice information is determined according to the time when the application set corresponding to the maximum probability was selected last time, that is, the application set with the latest time selected is used as the application set corresponding to the voice information. Of course, in practical application, it can be selected randomly. In addition, in order to improve the accuracy of application set selection, after an application set is selected in the application set, the correctness of a parsed text obtained by parsing voice information in the application set is determined, when the parsed text is correct, the selected times of the application set is increased by one, when the parsed text is wrong, the user is inquired about the application set corresponding to the voice information, the application set is searched in the application set, when the application set is searched, the selected times of the searched application set is increased by one, and if the application set is not searched in the application set, the application set is added to the application set information corresponding to the voice information, and the selected times of the application set is marked as 1.
Based on the above semantic parsing method, the present invention further provides a computer readable storage medium, where the computer readable storage medium stores one or more programs, and the one or more programs may be executed by one or more processors to implement the steps in the semantic parsing method according to the above embodiment.
Based on the above semantic parsing method, the present invention also provides a terminal device, as shown in fig. 5, which includes at least one processor (processor) 20; a display screen 21; and a memory (memory) 22, which may also include a communication interface (Communications Interface) 23 and a bus 24. Wherein the processor 20, the display 21, the memory 22 and the communication interface 23 may communicate with each other via a bus 24. The display screen 21 is configured to display a user guidance interface preset in the initial setting mode. The communication interface 23 may transmit information. The processor 20 may invoke logic instructions in the memory 22 to perform the methods of the embodiments described above.
Further, the logic instructions in the memory 22 described above may be implemented in the form of software functional units and stored in a computer readable storage medium when sold or used as a stand alone product.
The memory 22, as a computer-readable storage medium, may be configured to store a software program, a computer-executable program, such as program instructions or modules corresponding to the methods in the embodiments of the present disclosure. The processor 20 executes the functional applications and data processing, i.e. implements the methods of the embodiments described above, by running software programs, instructions or modules stored in the memory 22.
The memory 22 may include a storage program area that may store an operating system, at least one application program required for functions, and a storage data area; the storage data area may store data created according to the use of the terminal device, etc. In addition, the memory 22 may include high-speed random access memory, and may also include nonvolatile memory. For example, a plurality of media capable of storing program codes such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or a transitory storage medium may be used.
In addition, the specific processes that the storage medium and the plurality of instruction processors in the terminal device load and execute are described in detail in the above method, and are not stated here.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some of the technical features thereof can be replaced equivalently; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. A semantic parsing method, comprising:
when voice information is received, acquiring an application set corresponding to the voice information;
when the application set corresponding to the voice information is not obtained, searching the voice information in a preset voice information database;
if the voice information is not found, determining an application set corresponding to the voice information by adopting an LFM model, wherein the method specifically comprises the following steps: if the voice information is not found, acquiring an application set corresponding to the voice information; calculating the relevance between the voice information and each application set by adopting an LFM model, and determining the application set corresponding to the voice information according to the relevance;
the calculating the relevance between the voice information and each application set by adopting the LFM model, and determining the application set corresponding to the voice information according to the relevance specifically comprises the following steps:
extracting text information corresponding to the voice information, and acquiring weight information of the text information in each application set;
acquiring the interestingness of the user corresponding to the voice information for each application set, and determining the relevance between the voice information and each application set according to the interestingness and the weight information;
determining an application set corresponding to the voice information according to the correlation;
and analyzing the voice information in the application set to obtain an analysis text of the voice information.
2. The semantic parsing method according to claim 1, wherein when voice information is received, the obtaining the application set corresponding to the voice information specifically includes:
when voice information is received, analyzing the voice information to obtain text information corresponding to the voice information;
dividing the text information into a plurality of keywords, and determining an application set corresponding to the voice information according to each keyword obtained by dividing.
3. The semantic parsing method according to claim 1, wherein the obtaining the application set corresponding to the voice information if the voice information is not found specifically includes:
if the voice information is not found, extracting each keyword carried by the voice information;
and determining an application set corresponding to the voice information according to all the extracted keywords.
4. The semantic parsing method according to claim 1, wherein if the voice information is not found, determining the application set corresponding to the voice information by using an LFM model further comprises:
and associating the voice information with each application set, and storing the associated voice information in a preset voice information database.
5. The semantic parsing method of claim 1, wherein the method further comprises:
when the voice information is searched, extracting application set information corresponding to the voice information, wherein the application set information comprises application sets corresponding to the voice information and the duty ratio of each application set;
and determining the application set corresponding to the voice information according to the duty ratio of each application set.
6. The semantic parsing method according to claim 5, wherein the determining the application set corresponding to the voice information according to the duty ratio of each application set specifically includes:
and acquiring the duty ratio of each application set, and determining the application set corresponding to the voice information by adopting a preset linear predictor model.
7. A computer readable storage medium storing one or more programs executable by one or more processors to implement the steps in the semantic parsing method of any one of claims 1-6.
8. A terminal device, comprising: a processor, a memory, and a communication bus; the memory has stored thereon a computer readable program executable by the processor;
the communication bus realizes connection communication between the processor and the memory;
the processor, when executing the computer readable program, implements the steps of the semantic parsing method according to any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811643289.3A CN111401057B (en) | 2018-12-29 | 2018-12-29 | Semantic analysis method, storage medium and terminal equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811643289.3A CN111401057B (en) | 2018-12-29 | 2018-12-29 | Semantic analysis method, storage medium and terminal equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111401057A CN111401057A (en) | 2020-07-10 |
| CN111401057B true CN111401057B (en) | 2023-11-14 |
Family
ID=71432062
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811643289.3A Active CN111401057B (en) | 2018-12-29 | 2018-12-29 | Semantic analysis method, storage medium and terminal equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111401057B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105512323A (en) * | 2015-12-21 | 2016-04-20 | 广东省科技基础条件平台中心 | Method for recommending scientific and technological resources based on domain feature and latent semantic analysis |
| CN105786793A (en) * | 2015-12-23 | 2016-07-20 | 百度在线网络技术（北京）有限公司 | Method and device for analyzing semanteme of spoken language text information |
| CN106886430A (en) * | 2015-12-16 | 2017-06-23 | 芋头科技（杭州）有限公司 | The method and device that robot application program quickly starts |
| CN108021708A (en) * | 2017-12-27 | 2018-05-11 | 广州启生信息技术有限公司 | Content recommendation method, device and computer-readable recording medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9734193B2 (en) * | 2014-05-30 | 2017-08-15 | Apple Inc. | Determining domain salience ranking from ambiguous words in natural speech |
-
2018
- 2018-12-29 CN CN201811643289.3A patent/CN111401057B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106886430A (en) * | 2015-12-16 | 2017-06-23 | 芋头科技（杭州）有限公司 | The method and device that robot application program quickly starts |
| CN105512323A (en) * | 2015-12-21 | 2016-04-20 | 广东省科技基础条件平台中心 | Method for recommending scientific and technological resources based on domain feature and latent semantic analysis |
| CN105786793A (en) * | 2015-12-23 | 2016-07-20 | 百度在线网络技术（北京）有限公司 | Method and device for analyzing semanteme of spoken language text information |
| CN108021708A (en) * | 2017-12-27 | 2018-05-11 | 广州启生信息技术有限公司 | Content recommendation method, device and computer-readable recording medium |
Non-Patent Citations (1)
| Title |
|---|
| 基于LFM的音乐推荐系统的研究与实现;陈彪 等;中国优秀硕士学位论文全文数据库信息科技辑(第07期);第I138-1968页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111401057A (en) | 2020-07-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11720572B2 (en) | Method and system for content recommendation | |
| US11403680B2 (en) | Method, apparatus for evaluating review, device and storage medium | |
| US10997370B2 (en) | Hybrid classifier for assigning natural language processing (NLP) inputs to domains in real-time | |
| CN108829822B (en) | Media content recommendation method and device, storage medium and electronic device | |
| CN106649818B (en) | Application search intention identification method and device, application search method and server | |
| US11409813B2 (en) | Method and apparatus for mining general tag, server, and medium | |
| US9792279B2 (en) | Methods and systems for analyzing communication situation based on emotion information | |
| CN107480143B (en) | Method and system for segmenting conversation topics based on context correlation | |
| US20180349355A1 (en) | Artificial Intelligence Based Method and Apparatus for Constructing Comment Graph | |
| CN110929038B (en) | Knowledge graph-based entity linking method, device, equipment and storage medium | |
| WO2018049960A1 (en) | Method and apparatus for matching resource for text information | |
| US9245015B2 (en) | Entity disambiguation in natural language text | |
| CN102479191B (en) | Method and device for providing multi-granularity word segmentation result | |
| CN107291840B (en) | User attribute prediction model construction method and device | |
| CN109388743B (en) | Language model determining method and device | |
| CN114580382A (en) | Text error correction method and device | |
| CN107885717B (en) | Keyword extraction method and device | |
| CN111159412A (en) | Classification method and device, electronic equipment and readable storage medium | |
| KR101695014B1 (en) | Method for building emotional lexical information and apparatus for the same | |
| CN110263127A (en) | Text search method and device is carried out based on user query word | |
| CN113158687A (en) | Semantic disambiguation method and device, storage medium and electronic device | |
| CN117271736A (en) | Question-answer pair generation method and system, electronic equipment and storage medium | |
| CN111813993A (en) | Video content expanding method and device, terminal equipment and storage medium | |
| JP7172187B2 (en) | INFORMATION DISPLAY METHOD, INFORMATION DISPLAY PROGRAM AND INFORMATION DISPLAY DEVICE | |
| CN112926308B (en) | Method, device, equipment, storage medium and program product for matching text |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |